End of training

README.md

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.9238
-- Rouge1: 0.3437
-- Rouge2: 0.1943
-- Rougel: 0.3433
-- Rougelsum: 0.3414
-- Gen Len: 18.5833
+- Loss: 3.0348
+- Rouge1: 0.4278
+- Rouge2: 0.2495
+- Rougel: 0.4307
+- Rougelsum: 0.4272
+- Gen Len: 15.0833
 
 ## Model description
 
@@ -47,18 +47,21 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 8
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 7    | 4.5277          | 0.334  | 0.1958 | 0.3357 | 0.3321    | 17.8333 |
-| No log        | 2.0   | 14   | 4.2803          | 0.3437 | 0.1943 | 0.3433 | 0.3414    | 18.5833 |
-| No log        | 3.0   | 21   | 4.0983          | 0.3437 | 0.1943 | 0.3433 | 0.3414    | 18.5833 |
-| No log        | 4.0   | 28   | 3.9779          | 0.3402 | 0.1918 | 0.3389 | 0.3378    | 18.5833 |
-| No log        | 5.0   | 35   | 3.9238          | 0.3437 | 0.1943 | 0.3433 | 0.3414    | 18.5833 |
+| No log        | 1.0   | 7    | 3.7769          | 0.357  | 0.1943 | 0.3562 | 0.3538    | 18.6667 |
+| No log        | 2.0   | 14   | 3.5617          | 0.3952 | 0.2386 | 0.3963 | 0.3935    | 18.25   |
+| No log        | 3.0   | 21   | 3.3882          | 0.4045 | 0.2402 | 0.4094 | 0.4044    | 16.8333 |
+| No log        | 4.0   | 28   | 3.2644          | 0.4045 | 0.2402 | 0.4094 | 0.4044    | 16.8333 |
+| No log        | 5.0   | 35   | 3.1643          | 0.4316 | 0.2495 | 0.4345 | 0.4306    | 15.25   |
+| No log        | 6.0   | 42   | 3.0961          | 0.4278 | 0.2495 | 0.4307 | 0.4272    | 15.0833 |
+| No log        | 7.0   | 49   | 3.0551          | 0.4278 | 0.2495 | 0.4307 | 0.4272    | 15.0833 |
+| No log        | 8.0   | 56   | 3.0348          | 0.4278 | 0.2495 | 0.4307 | 0.4272    | 15.0833 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88c6789f793b2506fed73119f522a6d2704ea9281895a345dae14f1e60e3b496
+oid sha256:5730266f3d43c348ab10e4012a1d674154bf6eab150fa4918a25a982a11d217b
 size 242041896

runs/Jul09_02-36-24_1f47e4c6eb3f/events.out.tfevents.1720492585.1f47e4c6eb3f.2561.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c7600d5c471f5e5cae5a6eb38bf131d8cecff69a9d0c478359458b03c78d532
+size 10313

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d2f75b62857a2df1f64f31ea24ba3aa79d8eead5cc85ac851f560ceac3ceb8
+oid sha256:ed431872230b0468c247ba65fd26a15baa52856d9dd66cdd81ec136e3ab0c307
 size 5304